Complex background PCB mark point image detection method based on Mini ARU-Net network

The invention discloses a complex background printed circuit board mark point image detection method based on a Mini ARU-Net network. The method comprises the following steps: 1) collecting a printedcircuit board image, performing gray processing, extracting a mark point area as a mark point image, and adding a binary image of the area where a mark point is located as a segmentation label image;2) constructing a Mini ARUNet network, and inputting a mark point image for training and a segmentation label graph thereof into the Mini ARUNet network for training; 3) inputting a to-be-detected mark point image into the Mini ARUNet network obtained by training in the step 2) to perform mark point segmentation to obtain a segmentation result graph; and 4) solving the centroid of the area where the mark point is located according to the segmentation result graph, taking the centroid as the coordinate of the mark point, solving the average distance from the centroid to the edge of the area where the mark point is locat